def buildSpImageConverter(channelOrder, img_dtype):
"""
Convert a imageIO byte encoded image into a image tensor suitable as input to ConvNets
The name of the input must be a subset of those specified in `image.imageIO.imageSchema`.
:param img_dtype: the type of data the underlying image bytes represent
"""
with IsolatedSession() as issn:
# Flat image data -> image dimensions
# This has to conform to `imageIO.imageSchema`
height = tf.placeholder(tf.int32, [], name="height")
width = tf.placeholder(tf.int32, [], name="width")
num_channels = tf.placeholder(tf.int32, [], name="nChannels")
image_buffer = tf.placeholder(tf.string, [], name="data")
# The image is packed into bytes with height as leading dimension
# This is the default behavior of Python Image Library
shape = tf.reshape(tf.stack([height, width, num_channels], axis=0),
shape=(3,), name='shape')
if img_dtype == 'uint8':
image_uint8 = tf.decode_raw(image_buffer, tf.uint8, name="decode_raw")
image_float = tf.to_float(image_uint8)
elif img_dtype == 'float32':
image_float = tf.decode_raw(image_buffer, tf.float32, name="decode_raw")
else:
raise ValueError('''unsupported image data type "%s", currently only know how to
handle uint8 and float32''' % img_dtype)
image_reshaped = tf.reshape(image_float, shape, name="reshaped")
image_reshaped = imageIO.fixColorChannelOrdering(channelOrder, image_reshaped)
image_input = tf.expand_dims(image_reshaped, 0, name="image_input")
gfn = issn.asGraphFunction([height, width, image_buffer, num_channels], [image_input])
return gfn
def _addReshapeLayers(self, tf_graph, dtype="uint8"):
input_tensor_name = self.getInputTensor().name
gdef = tf_graph.as_graph_def(add_shapes=True)
g = tf.Graph()
with g.as_default():
# Flat image data -> image dimensions
height = tf.placeholder(tf.int32, [], name="height")
width = tf.placeholder(tf.int32, [], name="width")
num_channels = tf.placeholder(tf.int32, [], name="num_channels")
image_buffer = tf.placeholder(tf.string, [], name="image_buffer")
# Note: the shape argument is required for tensorframes as it uses a
# slightly older version of tensorflow.
shape = tf.reshape(tf.stack([height, width, num_channels], axis=0), shape=(3,),
name='shape')
if dtype == "uint8":
image_uint8 = tf.decode_raw(image_buffer, tf.uint8, name="decode_raw")
image_float = tf.to_float(image_uint8)
else:
assert dtype == "float32", "Unsupported dtype for image: %s" % dtype
image_float = tf.decode_raw(image_buffer, tf.float32, name="decode_raw")
image_reshaped = tf.reshape(image_float, shape, name="reshaped")
image_reshaped = imageIO.fixColorChannelOrdering(self.channelOrder, image_reshaped)
image_reshaped_expanded = tf.expand_dims(image_reshaped, 0, name="expanded")
# Add on the original graph
tf.import_graph_def(gdef, input_map={input_tensor_name: image_reshaped_expanded},
return_elements=[self.getOutputTensor().name],
name=USER_GRAPH_NAMESPACE)
# Flatten the output for tensorframes
output_node = g.get_tensor_by_name(self._getOriginalOutputTensorName())
_ = tf.reshape(output_node[0], # batch-size = 1,
shape=[-1], name=self._getFinalOutputOpName())
return g
def udf_impl(spimg):
import numpy as np
from tempfile import NamedTemporaryFile
from sparkdl.image.imageIO import imageArrayToStruct
img = imageIO.imageStructToPIL(spimg)
# Warning: must use lossless format to guarantee consistency
temp_fp = NamedTemporaryFile(suffix='.png')
img.save(temp_fp, 'PNG')
img_arr_reloaded = preprocessor(temp_fp.name)
assert isinstance(img_arr_reloaded, np.ndarray), \
"expect preprocessor to return a numpy array"
img_arr_reloaded = img_arr_reloaded.astype(np.uint8)
# Keras works in RGB order, need to fix the order
img_arr_reloaded = imageIO.fixColorChannelOrdering(
currentOrder='RGB', imgAry=img_arr_reloaded)
return imageArrayToStruct(img_arr_reloaded)
def udf_impl(spimg):
import numpy as np
from tempfile import NamedTemporaryFile
from sparkdl.image.imageIO import imageArrayToStruct
img = imageIO.imageStructToPIL(spimg)
# Warning: must use lossless format to guarantee consistency
temp_fp = NamedTemporaryFile(suffix='.png')
img.save(temp_fp, 'PNG')
img_arr_reloaded = preprocessor(temp_fp.name)
assert isinstance(img_arr_reloaded, np.ndarray), \
"expect preprocessor to return a numpy array"
img_arr_reloaded = img_arr_reloaded.astype(np.uint8)
# Keras works in RGB order, need to fix the order
img_arr_reloaded = imageIO.fixColorChannelOrdering(
currentOrder='RGB', imgAry=img_arr_reloaded)
return imageArrayToStruct(img_arr_reloaded)
def buildSpImageConverter(channelOrder, img_dtype):
"""
Convert a imageIO byte encoded image into a image tensor suitable as input to ConvNets
The name of the input must be a subset of those specified in `image.imageIO.imageSchema`.
:param img_dtype: the type of data the underlying image bytes represent
"""
with IsolatedSession() as issn:
# Flat image data -> image dimensions
# This has to conform to `imageIO.imageSchema`
height = tf.placeholder(tf.int32, [], name="height")
width = tf.placeholder(tf.int32, [], name="width")
num_channels = tf.placeholder(tf.int32, [], name="nChannels")
image_buffer = tf.placeholder(tf.string, [], name="data")
# The image is packed into bytes with height as leading dimension
# This is the default behavior of Python Image Library
shape = tf.reshape(tf.stack([height, width, num_channels], axis=0),
shape=(3, ),
name='shape')
if img_dtype == 'uint8':
image_uint8 = tf.decode_raw(image_buffer,
tf.uint8,
name="decode_raw")
image_float = tf.to_float(image_uint8)
elif img_dtype == 'float32':
image_float = tf.decode_raw(image_buffer,
tf.float32,
name="decode_raw")
else:
raise ValueError(
'''unsupported image data type "%s", currently only know how to
handle uint8 and float32''' % img_dtype)
image_reshaped = tf.reshape(image_float, shape, name="reshaped")
image_reshaped = imageIO.fixColorChannelOrdering(
channelOrder, image_reshaped)
image_input = tf.expand_dims(image_reshaped, 0, name="image_input")
gfn = issn.asGraphFunction([height, width, image_buffer, num_channels],
[image_input])
return gfn
def _addReshapeLayers(self, tf_graph, dtype="uint8"):
input_tensor_name = self.getInputTensor().name
gdef = tf_graph.as_graph_def(add_shapes=True)
g = tf.Graph() # pylint: disable=invalid-name
with g.as_default(): # pylint: disable=not-context-manager
# Flat image data -> image dimensions
height = tf.placeholder(tf.int32, [], name="height")
width = tf.placeholder(tf.int32, [], name="width")
num_channels = tf.placeholder(tf.int32, [], name="num_channels")
image_buffer = tf.placeholder(tf.string, [], name="image_buffer")
# Note: the shape argument is required for tensorframes as it uses a
# slightly older version of tensorflow.
shape_tensor = tf.stack([height, width, num_channels], axis=0)
shape = tf.reshape(shape_tensor, shape=(3, ), name='shape')
if dtype == "uint8":
image_uint8 = tf.decode_raw(image_buffer, tf.uint8, name="decode_raw")
image_float = tf.to_float(image_uint8)
else:
assert dtype == "float32", "Unsupported dtype for image: %s" % dtype
image_float = tf.decode_raw(image_buffer, tf.float32, name="decode_raw")
image_reshaped = tf.reshape(image_float, shape, name="reshaped")
image_reshaped = imageIO.fixColorChannelOrdering(self.channelOrder, image_reshaped)
image_reshaped_expanded = tf.expand_dims(image_reshaped, 0, name="expanded")
# Add on the original graph
tf.import_graph_def(
gdef,
input_map={input_tensor_name: image_reshaped_expanded},
return_elements=[self.getOutputTensor().name],
name=USER_GRAPH_NAMESPACE)
# Flatten the output for tensorframes
output_node = g.get_tensor_by_name(self._getOriginalOutputTensorName())
_ = tf.reshape(output_node[0], shape=[-1], name=self._getFinalOutputOpName())
return g
